agentmods.dev

8eyes

8eyes is a command for Claude Code from AgentBuildersApp/eight-eyes. It costs 12 tokens per session (815 once invoked), scanned A, original, MIT.

A command that starts an eight-role, failure-aware code review mission. It coordinates separate agents for implementation, testing, security, performance, accessibility, documentation, and other review work.

In plain words
What is it for?
Use it to run a multi-agent review of a coding objective, including test-driven development (writing tests around the change), security checks, accessibility checks, and blind review.
Why use it?
It turns a code review into a staged process with named roles, progress reports, and explicit approval before agents begin. This helps catch different kinds of problems that one reviewer might miss.

Command for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: mentions subagents.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the 8eyes plugin — 2 skills, 2 commands, 8 agents, 7 hooks shipped together

not rated 2 1mo ago A scan 12 tokens original MIT
View the source file AgentBuildersApp/eight-eyes
Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add AgentBuildersApp/eight-eyes
Claude Code
/plugin install 8eyes

Made for: Claude Code.

Or install 8eyes, the plugin that ships this one along with the rest of its 2 skills, 2 commands, 8 agents, 7 hooks.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for 8eyes

README.md
[![agentmods](https://agentmods.dev/badge/commands/agentbuildersapp/eight-eyes/8eyes.svg)](https://agentmods.dev/commands/agentbuildersapp/eight-eyes/8eyes)
Your own site
<a href="https://agentmods.dev/commands/agentbuildersapp/eight-eyes/8eyes"><img src="https://agentmods.dev/badge/commands/agentbuildersapp/eight-eyes/8eyes.svg" alt="Measured on agentmods" height="20"></a>
Per session 12 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 815 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00012 $0.00815
Opus 5 $0.00006 $0.00407
Sonnet 5 $0.00002 $0.00163
Haiku 4.5 $0.00001 $0.00081

Measured 6d ago against content hash e57e8b70b016, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

8eyes scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 6d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

commands/8eyes.md · 94 lines

How it starts

The opening of the file, as written. The whole thing — 94 lines — stays where its author put it; the contents beside it link to each section on GitHub.

8eyes Orchestrator

The user invoked this command with: $ARGUMENTS

This command is an execution workflow, not a prompt suggestion. You MUST follow the steps below in order. Do not collapse this into a single-agent review. Do not skip the Agent tool. Do not skip progress reporting.

Required Workflow

  1. FIRST ACTION: run this via the Bash tool: python3 ${CLAUDE_PLUGIN_ROOT}/scripts/collabctl.py init --objective "$ARGUMENTS" If the objective is missing, stop and ask the user for it instead of inventing one.
  2. Immediately run: python3 ${CLAUDE_PLUGIN_ROOT}/scripts/collabctl.py status Show the mission ID, objective, current phase, and the planned role order.
  3. Present the plan and WAIT for explicit user approval before spawning any subagent.
  4. Advance to implement, then spawn a NAMED collab-implementer subagent via the Agent tool. When it completes:
    • show a phase progress summary
    • show the per-role result block:
      • Role: implementer
      • Recommendation
      • Key findings
  5. Advance to test, then spawn a NAMED collab-test-writer subagent via the Agent tool. When it completes:
    • show a phase progress summary
    • show the per-role result block:
      • Role: test-writer
      • Recommendation
      • Key findings
  6. Advance to audit, then spawn these NAMED subagents in PARALLEL via the Agent tool:
    • collab-skeptic
    • collab-security
    • collab-performance
    • collab-accessibility Wait for all four results. After EACH role completes, show:
    • role name
    • recommendation
    • key findings After all four complete, show a combined audit progress summary.
  7. Advance to verify, then spawn a NAMED collab-verifier subagent via the Agent tool. When it completes:
    • show a phase progress summary
    • show the per-role result block:
      • Role: verifier
      • Recommendation
      • Key findings
  8. Finish with a final summary that reports findings per role and the overall recommendation.

Looping Rule

Read the full file on GitHub · 94 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 6d ago First seen · 94 lines · 12 tokens per session scan A e57e8b70b016

Subscribe to this mod's changes

8eyes is a command published in the GitHub repository AgentBuildersApp/eight-eyes (2 stars, last pushed 1mo ago), licensed MIT. It adds 12 tokens to every session and 815 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Code reviewSecurityai-code-reviewclaude-codecodex-clicopilot-clidefense-in-depth
Related

Other commands, from other repositories

pi-code-review

Adversarial code review via Codex — break confidence in changes, not validate them.

tznthou/claude-prism · 17 tokens

pi-askall

Ask both Codex and Gemini the same question — get three perspectives with Claude synthesis.

tznthou/claude-prism · 16 tokens

pi-fact-check

Fact-check content via Gemini search + Claude verification — cross-provider claim validation.

tznthou/claude-prism · 14 tokens

pi-ask-gemini

Ask Gemini a question — get Google's perspective alongside Claude's.

tznthou/claude-prism · 11 tokens

conventions-check

Check AGENTS.md, CLAUDE.md, and the projected agent artifacts (skills, subagents, commands) against the repo's conventions.

eugenelim/agent-ready-repo · 28 tokens

register-plugin-asset

新しい配布 command / agent / agent-skill を plugin manifest に登録し、検証シーケンスまで実行する.

s977043/river-review · 28 tokens